Please use this identifier to cite or link to this item:
https://hdl.handle.net/1959.11/22977
Title: | Real-time object detection in agricultural/remote environments using the multiple-expert colour feature extreme learning machine (MEC-ELM) | Contributor(s): | Sadgrove, Edmund (author) ; Falzon, Gregory (author) ; Miron, David (author) ; Lamb, David (author) | Publication Date: | 2018 | DOI: | 10.1016/j.compind.2018.03.014 | Handle Link: | https://hdl.handle.net/1959.11/22977 | Abstract: | It is necessary for autonomous robotics in agriculture to provide real time feedback, but due to a diverse array of objects and lack of landscape uniformity this objective is inherently complex. The current study presents two implementations of the multiple-expert colour feature extreme learning machine (MECELM). The MEC-ELM is a cascading algorithm that has been implemented along side a summed area table (SAT) for fast feature extraction and object classification, for a fully functioning object detection algorithm. The MEC-ELM is an implementation of the colour feature extreme learning machine (CF-ELM), which is an extreme learning machine (ELM) with a partially connected hidden layer; taking three colour bands as inputs. The colour implementation used with the SAT enable the MEC-ELM to find and classify objects quickly, with 84% precision and 91% recall in weed detection in the Y'UV colour space and in 0.5s per frame. The colour implementation is however limited to low resolution images and for this reason a colour level co-occurrence matrix (CLCM) variant of the MEC-ELM is proposed. This variant uses the SAT to produce a CLCM and texture analyses, with texture values processed as an input to the MEC-ELM. This enabled the MEC-ELM to achieve 78–85% precision and 81-93% recall in cattle, weed and quad bike detection and in times between 1 and 2s per frame. Both implementations were benchmarked on a standard i7 mobile processor. Thus the results presented in this paper demonstrated that the MEC-ELM with SAT grid and CLCM makes an ideal candidate for fast object detection in complex and/or agricultural landscapes. | Publication Type: | Journal Article | Source of Publication: | Computers in Industry, v.98, p. 183-191 | Publisher: | Elsevier BV | Place of Publication: | Netherlands | ISSN: | 1872-6194 0166-3615 |
Fields of Research (FoR) 2008: | 070104 Agricultural Spatial Analysis and Modelling 080104 Computer Vision 080109 Pattern Recognition and Data Mining |
Fields of Research (FoR) 2020: | 300206 Agricultural spatial analysis and modelling 460304 Computer vision |
Socio-Economic Objective (SEO) 2008: | 960904 Farmland, Arable Cropland and Permanent Cropland Land Management 960804 Farmland, Arable Cropland and Permanent Cropland Flora, Fauna and Biodiversity |
Socio-Economic Objective (SEO) 2020: | 180606 Terrestrial biodiversity 180603 Evaluation, allocation, and impacts of land use |
Peer Reviewed: | Yes | HERDC Category Description: | C1 Refereed Article in a Scholarly Journal |
---|---|
Appears in Collections: | Journal Article School of Science and Technology |
Files in This Item:
File | Description | Size | Format |
---|
SCOPUSTM
Citations
33
checked on Dec 21, 2024
Page view(s)
2,750
checked on Mar 3, 2024
Download(s)
4
checked on Mar 3, 2024
Items in Research UNE are protected by copyright, with all rights reserved, unless otherwise indicated.